8GB · AI Score 2.1/100 · first-party measured on 12 AI workloads
2.1 AI Score ✓ Measured
Every number on this page is first-party: NVIDIA GeForce RTX 3070 Founders Edition was run on our pinned 12-workload AI suite on 2026-07-11, with under 0.5% run-to-run variance. On Llama 3.1 8B (Q4_K_M) NVIDIA GeForce RTX 3070 Founders Edition delivers about 80.95 tokens/sec. Llama 3.3 70B does not fit. It needs roughly 42GB and this card has 8GB. For image generation, SDXL runs at 1.52 it/s, while FLUX.1-dev won't fit at BF16 (needs ~26GB). 9 of the 12 workloads won't fit on 8GB at the tested precision, Qwen2.5-Coder 14B, Qwen3 32B, Llama 3.3 70B, Z-Image Turbo and others. We publish those as hard gates rather than quietly dropping to a smaller quant.
Interesting card to bench, it actually pulled 240W on Llama 3.1 8B, which is 109% of its 220W rating, so don't size your PSU off the spec sheet. Same 8GB wall as the 3060 Ti though: 9 of 12 workloads gated. For LLMs it's fine at the small end and that's about it. Quick note on the setup: all my AI benchmarking was done on rented cloud GPUs, I used all three of Vast.ai, RunPod and Modal depending on which had the card, and they all have their pros and cons. Same pinned harness on every run, and everything here got double-checked before it went up.
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Qwen3 4B | 126.36 tok/s | 2.6 GB peak154 W55°C0.82 tok/WQ4_K_M | ✓ Measured |
| Llama 3.1 8B | 80.95 tok/s | 4.8 GB peak199 W60°C0.41 tok/WQ4_K_M | ✓ Measured |
| Qwen2.5-Coder 14B | ✕ Won't fit needs ~11.5 GB | VRAM-gated at this precision | ✓ Measured |
| Qwen3 32B | ✕ Won't fit needs ~23 GB | VRAM-gated at this precision | ✓ Measured |
| Llama 3.3 70B | ✕ Won't fit needs ~46 GB | VRAM-gated at this precision | ✓ Measured |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Stable Diffusion XL | 3.04 images/min | 6.5 GB peak177 W68°C19.7 s/img | ✓ Measured |
| Z-Image Turbo | ✕ Won't fit needs ~13 GB | VRAM-gated at this precision | ✓ Measured |
| FLUX.1 dev | ✕ Won't fit needs ~26 GB | VRAM-gated at this precision | ✓ Measured |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| FLUX.1 Kontext dev | ✕ Won't fit needs ~26 GB | VRAM-gated at this precision | ✓ Measured |
| Qwen-Image-Edit | ✕ Won't fit needs ~42 GB | VRAM-gated at this precision | ✓ Measured |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| LTX-Video (distilled) | ✕ Won't fit needs ~14 GB | VRAM-gated at this precision | ✓ Measured |
| Wan 2.2 5B (720p) | ✕ Won't fit needs ~18 GB | VRAM-gated at this precision | ✓ Measured |
| Architecture | Ampere |
| CUDA cores | 5,888 |
| VRAM | 8GB GDDR6 |
| Memory bus | 256-bit |
| Memory bandwidth | 448 GB/s |
| Boost clock | 1,725 MHz |
| TDP | 220 W |
| Process | 8nm |
| Interface | PCIe 4.0 x16 |
| Release date | 2020-10-29 |
| Launch MSRP | $499 |
NVIDIA GeForce RTX 3070 Founders Edition scores 2.1/100, #83 of 102. It ran 3 of 12; 9 exceeded its 8GB. Every figure here is our own measurement.
100% = this card, AI & Machine Learning headline metric (AI Score). #43 of 61 desktop cards in this vertical.
| GPU | Relative | % | AI Score |
|---|---|---|---|
| NVIDIA GeForce RTX 3080 | 110% | 2.3 | |
| NVIDIA GeForce RTX 2080 Ti Founders Edition | 105% | 2.2 | |
| NVIDIA GeForce RTX 3070 Ti | 105% | 2.2 | |
| NVIDIA GeForce RTX 2080 Super | 100% | 2.1 | |
| NVIDIA GeForce RTX 3070 Founders Edition | 100% | 2.1 | |
| NVIDIA GeForce RTX 5060 | 100% | 2.1 | |
| NVIDIA GeForce RTX 2070 SUPER | 95% | 2 | |
| NVIDIA GeForce RTX 2080 Founders Edition | 95% | 2 | |
| NVIDIA GeForce RTX 3060 Ti | 95% | 2 |
Same card, other workloads: NVIDIA GeForce RTX 3070 Founders Edition Gaming benchmarks
← All AI & Machine Learning GPU rankings
| Transistors | 17,400 million |
| Die size | 392.5 mm² |
| Fabricated by | Samsung |
| Transistor density | 44.3 million per mm² |
Denser than 42% of the 76 cards we have silicon data for. Density is the clearest measure of what a process node bought: a card that gained it without growing the die got its speed from the fab rather than the architecture.
Silicon figures from Wikipedia (CC BY-SA 4.0). Benchmarks on this page are our own. Compare every chip.
Whole-job timings, composed from our measured per-model results on this card.
Can't run: 60-second AI short film (needs Qwen3 32B), 60-second AI short film, narrated (needs Qwen3 32B), 10 short social clips (needs Qwen3 32B), 40-product photo shoot (needs FLUX.1 Kontext dev), 6-panel comic page (needs Qwen3 32B), 20 long-form articles (needs Llama 3.3 70B), Full codebase review (needs Qwen2.5-Coder 14B), Character sheet, 12 poses (needs FLUX.1 dev), 100-photo restoration batch (needs FLUX.1 Kontext dev), 24-frame storyboard (needs Qwen3 32B), 100-photo restore and enlarge (needs FLUX.1 Kontext dev).
This card is $499 to buy. The cheapest listed rate on Vast.ai is $0.049/hour, but that is the floor: we budget $0.059/hour, a 20% premium, because idle time, storage and unavailable cheap instances all land on the same bill. At that rate buying wins after 8,486 GPU-hours. Below it you are paying for idle silicon.
| How you would use it | GPU-hours a year | Rental cost a year | Time to break even |
|---|---|---|---|
| 2 hours a day, hobby | 730 | $43 | 11.6 years |
| 8 hours a day, working on it | 2,920 | $172 | 2.9 years |
| 24/7, always-on agent | 8,760 | $515 | 11.6 months |
At hobby usage this card is very unlikely to pay for itself before it is superseded. Rent it. Rental figures include a 20% premium over the cheapest listed rate. Ignores electricity, resale and the fact that a rented card can be a newer one tomorrow.
Cheapest of the RunPod and Vast on-demand rates we see, sampled daily. Spot and interruptible pricing runs lower.